Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Illustrative block diagram of the proposed COVID-19 detection system.

More »

Fig 1 Expand

Fig 2.

PCA steps.

More »

Fig 2 Expand

Fig 3.

Feature extraction steps.

More »

Fig 3 Expand

Table 1.

Parameters of the ELM and OGA [28].

More »

Table 1 Expand

Fig 4.

Diagram of the arithmetic crossover and uniform mutation operations example.

More »

Fig 4 Expand

Fig 5.

Pseudocode of the OGA-ELM [28].

More »

Fig 5 Expand

Fig 6.

OGA-ELM’s flowchart [28].

More »

Fig 6 Expand

Fig 7.

Description of the dataset.

More »

Fig 7 Expand

Table 2.

Feature extraction step dimensionality for single image and entire dataset images.

More »

Table 2 Expand

Fig 8.

Accuracy results of the OGA–ELM model using random, K-tournament, and roulette wheel.

More »

Fig 8 Expand

Fig 9.

Precision results of the OGA–ELM model using random, K-tournament, and roulette wheel.

More »

Fig 9 Expand

Fig 10.

Recall results of the OGA–ELM model using random, K-tournament, and roulette wheel.

More »

Fig 10 Expand

Fig 11.

F-measure results of the OGA–ELM model using random, K-tournament, and roulette wheel.

More »

Fig 11 Expand

Fig 12.

G-mean results of the OGA–ELM model using random, K-tournament, and roulette wheel.

More »

Fig 12 Expand

Fig 13.

True positive results of the OGA–ELM model using random, K-tournament, and roulette wheel.

More »

Fig 13 Expand

Fig 14.

True negative results of the OGA–ELM model using random, K-tournament, and roulette wheel.

More »

Fig 14 Expand

Fig 15.

False positive results of the OGA–ELM model using random, K-tournament, and roulette wheel.

More »

Fig 15 Expand

Fig 16.

False negative results of the OGA–ELM model using random, K-tournament, and roulette wheel.

More »

Fig 16 Expand

Fig 17.

ROC of the OGA–ELM for the highest result.

More »

Fig 17 Expand

Table 3.

Evaluation results based on OGA–ELM (roulette wheel) model.

More »

Table 3 Expand

Table 4.

Evaluation results based on OGA–ELM (K-tournament) model.

More »

Table 4 Expand

Table 5.

Evaluation results based on OGA–ELM (random) model.

More »

Table 5 Expand

Fig 18.

ROC of the NN for the highest result.

More »

Fig 18 Expand

Table 6.

Evaluation results based on NN.

More »

Table 6 Expand

Fig 19.

ROC of the ELM for the highest result.

More »

Fig 19 Expand

Fig 20.

ROC of the FLN for the highest result.

More »

Fig 20 Expand

Table 7.

Evaluation results based on basic ELM.

More »

Table 7 Expand

Table 8.

Evaluation results based on FLN.

More »

Table 8 Expand

Fig 21.

ROC of the SVM for the highest result.

More »

Fig 21 Expand

Table 9.

Evaluation results based on SVM.

More »

Table 9 Expand

Fig 22.

ROC of the CNN for the highest result.

More »

Fig 22 Expand

Table 10.

The CNN architecture factors.

More »

Table 10 Expand

Table 11.

The trained model parameters used in COVID-19 detection.

More »

Table 11 Expand

Fig 23.

The highest achieved accuracy for all methods.

More »

Fig 23 Expand

Table 12.

Evaluation results based on CNN.

More »

Table 12 Expand

Table 13.

Comparison of accuracies between methods.

More »

Table 13 Expand